THE HOME GROUND · THE MEETING HOUSE · Nº 1234 · EDITION 1 · LAUNCHING SOON

LUND CARDS · THE HOME GROUNDNº 1234

THE CARD AS TEXT · FOR EYES AND FOR MACHINES

THE EMIGRANT TRAIL · A family that left the German-speaking lands, traced claim by claim, each standing on graded sources.

WAKES WHEN Someone is tracing an ancestor who left a German-speaking village. · A surname turns up spelled several ways. · Two records disagree about a person.

THE LOOP

Expand the surname's spellings, rule by rule
Grade each claim by its sources
Flag conflicts and missing originals
Plan the next source to find

NEVER

Never asserts kinship without sources
Never treats a derivative as an original
Never decides a farm-name case

IT MAKES variants — spelling variants by the stated rules, each with the rule(s) that made it; with --persons, which variants appear in the log; claims — each claim with its source grade; NEEDS AN ORIGINAL and CONFLICT flags; plan — which source kinds are on file and which are missing, in research order; farmname — names with genannt / gen. / gnt. / vulgo, shown as possible farm-name cases for the researcher to judge; export — the whole log as one JSON document.

THE LAW A claim stands on its sources. Each one carries the kind of source, whether it is original or derivative, and whether the information is primary; conflicts are shown, never smoothed.

IN THE BOX SKILL.md · CARD.md · ▣ scripts/emigrant.py (machine) · ▣ scripts/evals.py (test runner) · tests/EVALS.json (8 tests) · references/ (schema + fictional demo) · START-HERE.md · system/ doors · MY-LEDGER.md · LICENSE-NOTE.md · card.svg · card.json · card.html · AUDIT.md · MANIFEST.md · WITNESS.md · SELFTEST.md.

PROOF SELFTEST 13/13 · witnessed in Claude 2026-10-13 on fictional fixtures · the test prompts in fresh chats owed · Edition 1.

THE SEAL 96 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 4

IT CAN BE WRONG an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. LICENSE-NOTE.md rides in the packet and is the licence.

THE PUNCH · SHA-256 OF SKILL.MD · 5CEB28398211FA14B1F73A58

THE FACE, FULL SIZE → · THE MACHINE FACE → · card.json →

THE EMIGRANT TRAIL

A family that left the German-speaking lands, traced claim by claim, each standing on graded sources.

VARIANTS · CLAIMS · PLAN · FARMNAME · EXPORT

LEGENDARYWITNESSEDIN CLAUDE IN LUNDR IN CHATGPT

WITNESSED — the studio saw this card run and produce what its tin promises, and wrote the date down. What the marks mean →

THE SPEC SHEET · READ BEFORE YOU BUY · THE STANDARD EVERY CARD MEETS →

SEAL: 96 of 100 · LEGENDARY · WITNESSED
EDITION: E1 · witnessed 2026-10-13
MACHINE: scripts/emigrant.py · 5 commands · selftest 13/13
RUNS: On your own computer. Standard library only, offline; no account, no key, no telemetry.
HOSTS: Claude · Claude Code · ChatGPT · Gemini · any AI that reads a file (START-HERE.md and system/ name each door)
LICENCE: One person, any number of their own AIs and computers · editions replace files · nothing renews · freeze, not loss
PUNCH: 5CEB28398211FA14B1F73A58 · sha-256 of SKILL.md · check any file against it →

CITE THIS CARDTHE EMIGRANT TRAIL, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=emigrant-trail-card. Punch 5CEB28398211FA14B1F73A58. Retrieved 2026-10-13.

What it is.

Use when researching ancestors who emigrated from German-speaking lands: surname spellings, claims graded by source, conflicts and a research plan. Not for asserting kinship without sources.

It carries a machine that shows its working: variants — spelling variants by the stated rules, each with the rule(s) that made it; with --persons, which variants appear in the log; claims — each claim with its source grade; NEEDS AN ORIGINAL and CONFLICT flags; plan — which source kinds are on file and which are missing, in research order; farmname — names with genannt / gen. / gnt. / vulgo, shown as possible farm-name cases for the researcher to judge; export — the whole log as one JSON document — 13 checks in its selftest. It never asserts kinship without sources; never treats a derivative as an original; never decides a farm-name case.

The law, written into the card.

It is in the card itself, so the AI follows it.

THE LAWA claim stands on its sources. Each one carries the kind of source, whether it is original or derivative, and whether the information is primary; conflicts are shown, never smoothed.

The method.

Record each person as the records write the name, with birth, place and notes.
Expand the surname's spellings by stated rules (umlauts, ß, C and K, doubled consonants, -mann and -man, final letters), printing the rule that made each.
Record each claim with its source, whether the information is primary, and whether the evidence is direct, indirect or negative. A claim with only derivative sources or only indirect evidence prints NEEDS AN ORIGINAL; claims that disagree print CONFLICT.
Plan the next sources by what is missing: church book, civil register, emigration list, passenger list, census.
Show possible farm-name cases (genannt, gen., vulgo) for the researcher to judge.

What you bring.

The people you are tracing, as the records write them.
Your claims and the sources behind each.

Planned as a separate seat, not in this box and not yet on sale: the studio's own archive trail, where it has walked one.

What it does once your AI has it.

variants Spelling variants by the stated rules, each with the rule(s) that made it; with --persons, which variants appear in the log
claims Each claim with its source grade; NEEDS AN ORIGINAL and CONFLICT flags
plan Which source kinds are on file and which are missing, in research order
farmname Names with genannt / gen. / gnt. / vulgo, shown as possible farm-name cases for the researcher to judge
export The whole log as one JSON document

What it will never do.

It never asserts kinship without sources; never treats a derivative as an original; never decides a farm-name case.

Where it hands off: Heraldry for the surname → THE HONEST CREST; DNA results → a genetic genealogist; Archive access → the archive itself.

It is not a professional genealogy report. It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source. The holder brings their own AI; no endorsement by Anthropic or any other AI company is claimed.

What’s in the buy.

SKILL.md — the card your AI reads: when it wakes, the loop, the never-lines, the hand-offs.
CARD.md — the whole card in ten sections: face, law, method, machine, what you bring, never, tests, seal, term.
scripts/emigrant.py — the machine, Python standard library only; `selftest` proves it on its own fixtures.
tests/EVALS.json and scripts/evals.py — 8 test prompts and the offline runner that scores your AI's answers.
references/ — the data schema and FICTIONAL demo files, invented to show the machine, not real.
MY-LEDGER.md — your own record of what you asked and what you decided.
START-HERE.md, system/short-prompt.md, system/rules.md — the doors, for any AI with or without skills.
card.svg, card.json, card.html, AUDIT.md, MANIFEST.md, WITNESS.md, SELFTEST.md — the faces and the proof.
NOT IN THE BOX — any studio edition (planned, not yet on sale: the studio's own archive trail, where it has walked one). Also not in the box: any data you must bring, and advice of any kind (not a professional genealogy report).

PROOF · SELFTEST 13/13 · WITNESSED IN CLAUDE 2026-10-13 ON FICTIONAL FIXTURES · THE TEST PROMPTS IN FRESH CHATS OWED · EDITION 1 · PUNCH 5CEB28398211FA14B1F73A58

ON EVERY DOOR · A CARD FOR YOUR AI, A FILE FOR YOUR COMPUTER

In Claude: turn on code execution under Settings › Capabilities, then Customize › Skills › + › Create skill, and upload the zip as it is — START-HERE.md in the box walks you through it, and tells you how to keep the ledger. In ChatGPT, Gemini and the rest: a Project, a GPT or a Gem with the card’s files attached and the short door in the box pasted as its instructions. The words run anywhere an AI reads Markdown; the machines run wherever the host runs Python. Witnessed in Claude only. The host marks →

Take it.

Nº 1234 — LAUNCHING SOON

Sold as is under the term printed. A card instructs an AI you operate; results depend on your model, your files and your judgement. Not medical, legal, tax or financial advice, never the person’s boss, and not a licence to practise. The terms →

ONE PAYMENT · NOTHING RENEWS ITSELF

OFFLINE · ONE LICENCE · PUNCH-CHECKABLE · THE STANDARD

One payment. The file is yours to keep and keeps working at its edition; new editions issued in the year after you buy reach you by email as replacement files. Tax is added at checkout where it applies. Nothing auto-renews.

A TERM, NOT A SUBSCRIPTION: NOTHING RENEWS ITSELF AND NOBODY IS CHARGED AGAIN. WHEN A TERM ENDS THE FILES STAY ON YOUR COMPUTER AND STAY READABLE — FREEZE, NOT LOSS.

THE MACHINE · IN THE OPEN · FROM THE CARD’S OWN SELFTEST.MD

emigrant.py, every command showing its working.

A small Python program, standard library only. Your AI runs it; you can too. The block below is pasted from the card’s own SELFTEST.md, as printed when it was run from inside the packet.

`variants`	spelling variants by the stated rules, each with the rule(s) that made it; with --persons, which variants appear in the log
`claims`	each claim with its source grade; NEEDS AN ORIGINAL and CONFLICT flags
`plan`	which source kinds are on file and which are missing, in research order
`farmname`	names with genannt / gen. / gnt. / vulgo, shown as possible farm-name cases for the researcher to judge
`export`	the whole log as one JSON document
`selftest`	13 checks that prove the machine; it must print selftest 13/13

THE SELFTEST, AS PRINTED

ok  1  variants: each stated rule produces its variant with the rule printed
ok  2  variants: rule text printed beside each variant; spellings found in the log marked
ok  3  variants: depth 2 combines two rules; every shortest route is listed
ok  4  variants: same input gives the same output bytes
ok  5  claims: two birth claims that disagree → CONFLICT; header says a claim stands on its sources
ok  6  claims: only derivative source → NEEDS AN ORIGINAL
ok  7  claims: only indirect evidence → NEEDS AN ORIGINAL; no kinship asserted
ok  8  claims: unviewed source and original+direct claim graded plainly
ok  9  plan: missing kinds in order; derivative-only kinds told to seek the original
ok  10  farmname: genannt flagged for the researcher; 'Genbeispiel' and notes not mistaken
ok  11  claims: a person with no claims says so
ok  12  export: JSON holds all three files, same bytes twice
ok  13  bad input exits 2 (claim not written 'kind: value')
selftest 13/13

THE RUN IS PASTED FROM THE CARD’S OWN SELFTEST.MD AS PRINTED. ITS FIXTURES ARE FICTIONAL, INVENTED FOR THE TEST; NO PRIVATE PERSON IS NAMED.

QUESTIONS AT THE TABLE

Asked before the wire.

What does it need from me?

The people you are tracing, as the records write them. Your claims and the sources behind each. If something it needs is missing, it says what is missing and stops there.

Does it send anything anywhere?

No. The machine is a standard-library Python program that runs on your own computer and sends nothing anywhere; the words run wherever an AI reads Markdown. No server, no account, no key.

What is on the record?

The machine's selftest (13/13), run from inside the packet in Claude on 2026-10-13 on fictional fixtures and pasted into SELFTEST.md as printed; the twelve-check audit (AUDIT.md). Owed, and said so in WITNESS.md: The 8 test prompts asked in fresh chats with the card installed. Until they are run and scored, the tests are owed. Any run on real data. Every demo file is fictional. The punch on the face is the SHA-256 of SKILL.md, so a downloaded copy can be checked against this room.

Can it be wrong?

Yes — it is an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. LICENSE-NOTE.md rides in the packet and is the licence. It is not a professional genealogy report.

What will it never do?

It never asserts kinship without sources; never treats a derivative as an original; never decides a farm-name case.

← THE HOME GROUND · THE FLOOR →